© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38795
    Prev
    Next
    INDEX
    Explanations

    <end_of_turn>

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bienvenidos
    0.47
     welcome
    0.39
    Welcome
    0.38
    ὃ
    0.37
    謚
    0.37
    Tomas
    0.37
    Islam
    0.37
    oslovens
    0.36
    Ocean
    0.36
     Основ
    0.36
    POSITIVE LOGITS
    ଉ
    0.39
    íme
    0.38
    ⴷ
    0.37
    сль
    0.36
     চলচ্চিত্রে
    0.36
     சார
    0.36
     ব্যাপারটা
    0.36
    াব
    0.36
    Charged
    0.35
    ्रांत
    0.35
    Activations Density 0.013%

    No Known Activations